© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 371
    Prev
    Next
    INDEX
    Explanations

    configuration options and layout attributes in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSlice
    -0.40
    PostInfinity
    -0.38
     rigue
    -0.38
     ddelweddau
    -0.37
    即
    -0.36
     怎样
    -0.36
    瘍
    -0.35
     wenigstens
    -0.33
     мәкалә
    -0.33
     zostanie
    -0.33
    POSITIVE LOGITS
    LEADING
    1.69
    TRAILING
    1.00
    CppMethod
    0.66
     Leading
    0.65
    Leading
    0.63
    ftagPool
    0.61
    DoubleQuotes
    0.60
    leading
    0.60
    tagHelperRunner
    0.59
    addGroup
    0.57
    Activations Density 0.021%

    No Known Activations